提示词
提示词工程与模板
reflection
davidkiss
"Analyzes the conversation and tool usage to propose improvements to skills or store user preferences."
fp-learn
Nlea
Add a learning layer to FP project planning. Use when the user asks to "plan with learning goals", "learn while building", "fp-learn", "add learning to plan", or wants to track what they're learning during a project. Wraps around fp-plan/fp-implement/fp-review to classify tasks as DIY or delegate, track progress per phase, and generate quizzes.
image-generation
QwenLM
Image generation skill based on Alibaba Cloud DashScope, supporting the creation of high-quality hand-drawn or standard images from user descriptions.
orchestrate
vkotios
Use when the user asks you to coordinate a work package with orch in an adopted repository and you are its controller. Do not activate for an orch-launched implementer or reviewer, or for development of the kit itself.
claude-usage
tdimino
Report ground-truth Claude token consumption and estimated cost by parsing JSONL session files directly. Use when checking API spend, auditing token usage by project/session/model, generating daily/weekly/monthly cost reports, or diagnosing ccusage undercounting. Includes subagent files that ccusage ignores.
parakeet
tdimino
Local speech-to-text via Handy app (push-to-talk) and NeMo CLI scripts. Parakeet V3: 25 languages, auto-detection, ~30x realtime on M4 Max, 6% WER. This skill should be used when transcribing audio files or dictating voice input.
skill-toggle
tdimino
Enable, disable, and manage Claude Code skills. Use when the user asks to enable/disable/toggle/manage skills, check skill status, list skills, manage skill collections, or clean up the skills directory.
skill-optimizer
tdimino
Guide for creating and reviewing skills. This skill should be used when users want to create a new skill, review an existing skill for quality, or optimize a skill that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
gemini-claude-resonance
tdimino
This skill enables cross-model dialogue between Claude and Gemini with shared visual memory. Use when the user wants to generate images, have visual dialogues with AI, create scientific illustrations with continuity, or have multiple AI perspectives respond to the same prompt. Key trigger phrases: "generate an image", "visual dialogue", "ask the daimones", "resonance field", "Minoan tarot", "cross-model", "KV cache", "MESSAGE TO NEXT FRAME".
architecture-md-builder
tdimino
"Build comprehensive ARCHITECTURE.md files for any repository following matklad's canonical guidelines. This skill should be used when creating codebase documentation that serves as a map for developers and AI agents, auditing existing repos for architectural understanding, or when users ask to 'document the architecture', 'create an architecture.md', or 'map this codebase'. Produces bird's eye views, ASCII/Mermaid diagrams, codemaps, invariants, and layer boundaries."
beautiful-mermaid
tdimino
Render Mermaid diagrams as ASCII/Unicode art for terminal display or as SVG files. Use when visualizing flowcharts, state machines, sequence diagrams, class diagrams, or ER diagrams. Supports 15 themes including tokyo-night, catppuccin, nord, dracula, and github.
open-interpreter
tdimino
Desktop GUI automation via OpenInterpreter — mouse, keyboard, screenshot,
codex-orchestrator
tdimino
Orchestrate OpenAI Codex CLI with specialized subagents for code review, debugging, architecture analysis, security audits, refactoring, and documentation. This skill should be used when delegating focused development tasks to Codex subagents (gpt-5.3-codex, gpt-5.3-codex-spark, gpt-5.2-codex) via AGENTS.md persona injection.
llama-cpp
tdimino
Secondary local LLM inference engine via llama.cpp. This skill should be used when running GGUF models directly, loading LoRA adapters for Kothar, benchmarking inference speed, or serving models via llama-server. Complements Ollama (which remains primary for RLAMA and general use).
skill-creator
brianlovin
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
claude-tracker-suite
tdimino
"Claude Code session management suite: search sessions by topic/ID, resume crashed sessions, monitor live sessions, detect projects, auto-summarize new sessions, and bootstrap new setups. This skill should be used when searching past sessions, checking running sessions, resuming work, or bootstrapping a new machine."
agents-md-manager
tdimino
This skill should be used when creating, auditing, or maintaining AGENTS.md files and Codex CLI configuration for any project—including initializing AGENTS.md for cross-agent compatibility (Codex, Cursor, Copilot, Devin, Jules, Amp, Gemini CLI), generating config.toml or .rules files, scaffolding .agents/skills/, converting CLAUDE.md to AGENTS.md, or auditing existing agent configs for bloat and staleness. Complementary to codex-orchestrator (which executes subagents; this skill creates the config files they consume).
linkedin-export
tdimino
Parse, search, analyze, and ingest LinkedIn GDPR data exports. This skill should be used when working with LinkedIn data — searching messages, analyzing connections, exporting to Markdown, or ingesting into RLAMA for semantic search. Requires a LinkedIn GDPR data export ZIP file.
super-ralph-wiggum
tdimino
Super Ralph Wiggum - autonomous iteration loops with templates, PRD support, progress tracking, and browser testing. This skill should be used when running Claude Code in autonomous loops for test coverage improvement, PRD-based feature development, documentation generation, dataset creation, lint fixing, code cleanup, or framework migrations. Combines the plugin's in-session loop mechanism with specialized templates and best practices from Geoffrey Huntley, Ryan Carson, and AI Hero.
claude-agent-sdk
tdimino
Build AI agents using the Claude Agent SDK. Covers query functions,
minoan-swarm
tdimino
Orchestrate Claude Code Agent Teams with Minoan-Semitic naming. This skill should be used when planning or launching multi-agent teams to tackle project phases, features, or complex tasks in parallel. It auto-discovers project context (CLAUDE.md, roadmaps, plans, issues) and generates named team configurations with structured task lists and file ownership.
codex-cto
tdimino
Inverted orchestration—Codex CLI acts as CTO (planning and reviewing), Claude Code executes with native tools. Use when a task benefits from external architectural oversight before and after implementation.
mcp-server-manager
tdimino
Configure and manage MCP (Model Context Protocol) servers in Claude Code CLI. Use this skill when adding, removing, listing, or troubleshooting MCP servers, or when questions arise about MCP configuration, transport types, scopes, or authentication. Essential for connecting Claude Code to external tools, databases, and APIs.
claude-md-manager
tdimino
Create, audit, and maintain CLAUDE.md documentation files that configure Claude Code for projects. Use this skill when (1) initializing a new project with Claude Code configuration, (2) reviewing or improving existing CLAUDE.md files, (3) organizing project instructions using progressive disclosure patterns, (4) converting repeated instructions into permanent documentation, or (5) setting up agent_docs/ structures for larger codebases. Handles the WHAT/WHY/HOW framework, conciseness optimization, and file import patterns.